The fluorescent lights of the office seemed to hum with a malevolent energy, mirroring the throbbing in Amelia's temples. She’d poured months into this damn project, sacrificing weekends, social life, and sanity. Now, staring at the presentation across the conference table, her stomach twisted. It was… hers. Nearly identical, down to the obscure research citations she'd painstakingly unearthed. Across from her, Mark, all smarmy smiles and overly-friendly gestures, beamed. He was the golden boy, the favored one.

Amelia’s jaw clenched. The urge to smash something, anything, was almost overwhelming. She forced a smile, a brittle thing that felt like shards of glass in her mouth. “Interesting,” she managed, her voice tight.

The blood in her veins felt like ice water. She focused on the grain of the conference table, trying to anchor herself to something, anything, besides the creeping tide of fury that threatened to drown her.

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