The noise of the cafe grated on her. She had come here to escape, to find a moment of peace. But the chatter, the clatter of cups, the insistent music – all amplified her already raw emotions. She picked up the book she had bought at the bookstore.

She flipped through the pages, her fingers drumming a restless rhythm against the cover. She needed to focus, to find an anchor.

A small, folded note slipped out. The words on the page blurred as she read them. Her hands clenched into fists. She felt a burning sensation in her throat. The paper crumpled in her grasp.

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