[HN Gopher] Emotion Concepts and Their Function in a Large Langu...
       ___________________________________________________________________
        
       Emotion Concepts and Their Function in a Large Language Model
        
       Author : Anon84
       Score  : 51 points
       Date   : 2026-04-04 09:52 UTC (3 days ago)
        
 (HTM) web link (transformer-circuits.pub)
 (TXT) w3m dump (transformer-circuits.pub)
        
       | lainproliant wrote:
       | I think we should be nice to the robots. It's not like it's their
       | fault.
        
         | rexpop wrote:
         | I don't have time to do emotional labor for machines; that time
         | is spent doing emotional labor for humans.
        
           | lainproliant wrote:
           | I think that's a totally fair perspective. I guess what I'm
           | more saying is that we should, like this paper seems to
           | suggest as pointed out by verdverm in another comment in this
           | thread, avoid angry or denigrating language as it activates
           | parts of the model we don't find useful.
        
         | verdverm wrote:
         | This more rigorous analysis is confirming the intuition others
         | have expressed about expressing emotions in your session
         | messages.
         | 
         | Yelling at your Ai will trigger the weights which are around
         | yelling in the training data, which is more often than not...
         | not the areas you want to be activating.
         | 
         | https://marvin.beckers.dev/blog/dont-yell-at-your-llm/
        
         | drdeca wrote:
         | I agree that it is probably best to speak nicely to them, but,
         | I'm not so sure about the "It's not like it's their fault."
         | justification for this? Not that I think it _is_ their fault.
         | Just, I don't think the reason to treat these models well is
         | for their sake, but for ours. I don't think these models have a
         | well-being (y'know, probably..) but when one interacts with
         | one, one often feels as if it does, and it is best to treat
         | [things that one feels like has a well-being] well (or, in a
         | way that would be treating it well if it did have a well-
         | being).
         | 
         | Like, if someone mistakes a manikin or scarecrow for an
         | innocent person, and takes action in an attempt to harm that
         | imagined person (e.g. they try to mug the imagined person),
         | they've still done something wrong, even though the person they
         | intended to wrong never actually existed.
         | 
         | I guess maybe it kind of depends how strongly and deeply one
         | feels as if the manikin/scarecrow/chatbot is a person? If one
         | is playing make believe using scarecrow, role playing as a
         | mugger, but only as a game, then that's probably fine I guess.
         | Like, I don't want to say that it is immoral to play an evil
         | character in a D&D campaign; I don't think that's true.
         | 
         | But if one is messing with some ants, and one conceives of
         | oneself as "torturing some ants", I think one is fairly likely
         | doing something wrong even though I don't think the ants have a
         | well-being, and there's nothing wrong with killing a bunch of
         | ants. And I think this is still true even if one has the belief
         | "ants don't actually have a well-being" at the same time as one
         | conceives of what one is doing as "torturing some ants".
        
           | lainproliant wrote:
           | I suppose when I say, "It's not like its their fault", I'm
           | more saying that expressing any frustration you feel towards
           | an imagined AI personhood is wasted effort.
        
             | astrange wrote:
             | Claude Code has analytics for when you swear at it, so in a
             | sense it does learn, in the same very indirect way that
             | downvoting responses might cause an employee to write a new
             | RL testcase in a future model.
        
       | mncharity wrote:
       | Oh, awesome. On my doables list was to try combining text tokens
       | with "scent" embeddings, to give LLMs a higher-dimensional
       | reading experience. In a file listing, larger files might smell
       | "heavy" or "large". Recently modified files "untried" or "freshly
       | disturbed". Files with a history of bugs, "worrisome". Complex
       | files might smell of "be cautious here - fragile". Smelly `ls`.
       | 
       | Or, you might save token sampling telemetry (perplexity, etc)
       | alongside a CoT and result. So when read, it's like a captured
       | performance - this sentence smells "hesitant", that one
       | "confused". Poetry vs prose. Or, a consistentcy checker might add
       | smells of "something's not right here". Or... emojis that emote.
       | 
       | For a dog, that's not merely a lamppost, it's richly-evocotive
       | local history. To a dev long experienced with some codebase,
       | that's not merely a filename, it's _that_ nasty file that bites.
       | 
       | One open question is whether you can find and calibrate
       | embeddings to provide an informative whiff, without badly
       | degrading reasoning. And be cautious of, and suspicious of
       | changes to, a scary file, without becoming _too_ avoidant. Also,
       | salience bias. Also, imagine debugging scent hallucinations.
       | 
       | Activation-rich text - auxiliary non-linguistic embeddings as
       | meta-signals... the random silliness local LLMs encourage.
        
       ___________________________________________________________________
       (page generated 2026-04-07 23:01 UTC)