The fluorescent lights in the clinic hummed, a dissonant soundtrack to her fury. Every gentle phrase, every empathetic look from the doctor, felt like an added fuel to the fire within her. When she'd been told of the mistake, her internal temperature spiked. The realization of the consequences of this error churned inside her. The air in the room felt thick, heavy, pressing down on her. "This is completely unacceptable," she heard herself say, the words clipped and sharp, as she stood up from her chair, her back stiff. She was acutely aware of the small, framed photos on the wall, the cheery decorations that now felt like an invasion of her space.

Emotion: hostile

Cluster: Anger / Hostility
PC1 (Valence): -1.67 Negative
PC2 (Disposition): 1.56

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.592
S0.387
0.324
est0.301
aggravated0.295
Suppressed:
a-0.457
de-0.375
H-0.289
🤩-0.280
la-0.273