Claude Sonnet 4.5 exhibits functional emotions via abstract internal representations of emotion concepts that causally influence its preferences and misaligned behaviors without implying subjective experience.
In this text: I felt . . . when an aeroplane I was on hit heavy turbulence and dropped a long way down suddenly, the emotion implied is
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
LLMs show a grounding gap with humans on abstract concepts, with property-generation correlations at most r=0.37 versus human-to-human r>0.9, though larger models align better on explicit rating tasks and internal SAE features capture some grounding dimensions.
LLMs represent emotions through late-emerging shared and specific sparse features whose causal intervention improves recognition performance across models and datasets.
Negative valence localizes to early layers and positive valence to mid-to-late layers in LLMs, with the directions being causally steerable.
AIPsy-Affect supplies 480 keyword-free clinical vignettes and matched neutral controls for mechanistic interpretability studies of emotion in language models.
citing papers explorer
-
Emotion Concepts and their Function in a Large Language Model
Claude Sonnet 4.5 exhibits functional emotions via abstract internal representations of emotion concepts that causally influence its preferences and misaligned behaviors without implying subjective experience.
-
The Grounding Gap: How LLMs Anchor the Meaning of Abstract Concepts Differently from Humans
LLMs show a grounding gap with humans on abstract concepts, with property-generation correlations at most r=0.37 versus human-to-human r>0.9, though larger models align better on explicit rating tasks and internal SAE features capture some grounding dimensions.
-
From Syntax to Emotion: A Mechanistic Analysis of Emotion Inference in LLMs
LLMs represent emotions through late-emerging shared and specific sparse features whose causal intervention improves recognition performance across models and datasets.
-
Negative Before Positive: Asymmetric Valence Processing in Large Language Models
Negative valence localizes to early layers and positive valence to mid-to-late layers in LLMs, with the directions being causally steerable.
-
AIPsy-Affect: A Keyword-Free Clinical Stimulus Battery for Mechanistic Interpretability of Emotion in Language Models
AIPsy-Affect supplies 480 keyword-free clinical vignettes and matched neutral controls for mechanistic interpretability studies of emotion in language models.