claim
active
claim:emotion-vector-geometry-mirrors-human-psychology-with-valence-and-arousal-axesEmotion vector geometry mirrors human psychology with valence and arousal axes
Sanity check, not surprising.
Source paper
extracted_from(2026) · Nicholas Sofroniew · Isaac Kauvar · William Saunders · Runjin Chen +12
Neighborhood — ranked by edge-count
Papers (1)
paper
Findings (3)
finding
- Intuitive groupings.
- Geometry mirrors human psychology.
- Geometry mirrors human psychology.
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.
- Linear representations of emotion concepts extracted from activations.
- Illustrates how the same empirical finding is read differently by computational functionalists and organismic functionalists.
- Interpretation of Part 2.
- If LLM emotion representations resemble human valence-arousal space, behavior and activations will follow distances in that spacehypothesis0.780Prediction from circumplex theory.
- Cited as activation-level support for the performing care vs having care distinction the battery detects behaviorally
- Interprets the Sofroniew et al. findings within the Level 2 indicator table.
- Steering effect size across 35 emotion vectors correlates with probe-preference correlation at r=0.85finding0.774Emotions correlating with preference causally drive it.
- Representations of an emotion that is implied but not expressed.