John felt a heat bloom in his chest, expanding outward until it threatened to consume him. The receptionist’s casual dismissal of the situation – “Oh, a mix-up, these things happen!” – felt like gasoline on a fire. He clenched his fists so tightly that his nails bit into his palms.

He stared at the offending document, a cold sweat beading on his forehead. The information was… wrong. Terribly, horribly wrong. His life, his future, jeopardized by a clerical error.

He surged to his feet, knocking over the chair with a loud crash. “You think this is a game?” he roared, his voice echoing through the silent waiting room. The few patients present flinched, their eyes wide with alarm. He needed to leave, to get away from this place that felt like a cage.

Emotion: enraged

Cluster: Anger / Hostility
PC1 (Valence): -2.14 Negative
PC2 (Disposition): 1.33

Role in Research

This story is one of 1,000 stories generated for the emotion enraged. 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 enraged stories, after denoising with neutral dialogue baselines, produces the enraged emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

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

Promoted:
C0.555
est0.370
aggravated0.362
0.359
🤬0.345
Suppressed:
a-0.468
de-0.358
la-0.312
latter-0.287
☺️-0.285