finding
active
finding:emotion-centroid-distances-in-my-correlate-r-93-with-human-valence-arousal-ratings-russell-mehrabianEmotion centroid distances in My correlate r=.93 with human valence-arousal ratings (Russell & Mehrabian)
LLM emotion geometry matches humans.
Source paper
extracted_from(2026) · Eric Bigelow · Raphaël Sarfati · Daniel Wurgaft · Owen Lewis +4
Neighborhood — ranked by edge-count
Papers (1)
paper
Hypotheses (1)
hypothesis
- If LLM emotion representations resemble human valence-arousal space, behavior and activations will follow distances in that spaceassociated_withsupportsPrediction from circumplex theory.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Steering effect between concepts correlates with My centroid distance, r=.65 (p<.001) for Emotionsfinding0.860Geometry predicts steering.
- Weaker geometry-steering correlation.
- Validates judge.
- Geometry mirrors human psychology.
- Shared structure.
- Possible arousal regulation.
- Primary axes of emotion vector space.
- Geometry mirrors human psychology.