The phone call from her mother had been short. “I’m sorry, honey,” she’d said, her voice strained. “I know how much this means to you.” Now, in the library, she gripped the worn spine of her textbook so tightly her knuckles were white. The air felt thick, suffocating. Every breath was a struggle. Her eyes flickered over the words, but they wouldn't register, the print blurring into an incomprehensible mess. She slammed the book shut, the sound a sharp crack in the hushed silence. She wanted to scream, to shatter the quiet.

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