The fluorescent lights of the accounting department seemed to hum a mocking tune, a constant reminder of the injustice. Brenda slammed her stapler onto the desk, the metal clattering echoing in the otherwise silent room. Her knuckles were white as she gripped the edges of her monitor. After five years, *five years* of meticulously balancing budgets, she was being shoved into…marketing? It was an insult.

A slow burn crept up her neck, a physical manifestation of her fury. She imagined flaying the head of the man who decided this, slowly, painfully. His smug face, the way he always seemed to be laughing *at* her. Her jaw clenched so hard she thought her teeth might crack.

She shoved her chair back, the wheels squealing in protest. Grabbing her purse, she stomped towards the exit, ignoring the surprised glances from her colleagues. They didn't understand. They couldn't.

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