The doctor, thankfully, seemed sympathetic. She had explained, in hushed tones, the difficulties of her situation. She had expected a shared sense of understanding, a sense of relief from the burden of her illness. Then he arrived, a whirlwind of positivity and breezy pronouncements about "living your best life" despite the challenges. She felt a heat rise in her cheeks. His upbeat demeanor, his eagerness to share his "secrets" for managing the condition, felt… patronizing. She focused on the pattern of the wallpaper, anywhere but at his smiling face.

Emotion: offended

Cluster: Anger / Hostility
PC1 (Valence): -1.20 Negative
PC2 (Disposition): 1.44

Role in Research

This story is one of 1,000 stories generated for the emotion offended. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 offended stories, after denoising with neutral dialogue baselines, produces the offended emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the offended vector is projected through the unembedding matrix.

Promoted:
l0.348
0.266
😡0.260
🤬0.259
0.257
Suppressed:
adventurous-0.225
давно-0.219
soon-0.210
🤩-0.207
warmly-0.203