The coach's words felt like a punch to the gut. It had all been for naught. After months of grueling training, after all the missed parties and social gatherings, Liam felt a sharp, bitter pang.

He stood frozen, unable to respond, a storm of emotions churning inside. He was left in the wake of the news, utterly lost. He wanted to scream, to yell.

He slowly and deliberately collected his gear, his movements stiff and mechanical, each action a stark betrayal. He turned and left the gym, the silence amplifying the echo of his disappointment.

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