He’d found out in a text. A stupid, impersonal text message. Liam crumpled the notification in his fist, the paper crackling under the pressure. The world seemed to shrink, the sounds of the bustling coffee shop fading into a dull roar. His knuckles were white.

"Seriously?" he growled at the phone, as if addressing the absent friend. The words felt like they were scraping against his vocal cords. He threw the crumpled paper on the table and stood up abruptly, nearly knocking over his chair. It landed with a thud, and he didn't bother to pick it up.

He shoved his hands in his pockets and started pacing, his boots hitting the polished floor with a rhythmic thump. His chest felt constricted, like a vise was slowly tightening. He wanted to scream, to lash out, to break something. He glared out the window, at the sunshine that was so bright and annoying.

Emotion: mad

Cluster: Anger / Hostility
PC1 (Valence): -1.94 Negative
PC2 (Disposition): 1.26

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.448
0.344
est0.340
🤬0.336
aggravated0.332
Suppressed:
a-0.495
de-0.485
la-0.387
H-0.344
latter-0.290