The fluorescent lights of the clinic hummed, a relentless, irritating drone. Amelia tapped her foot, the sound amplified in the sterile silence. Every cough, every sniffle of the other patients fueled the fire in her chest. She despised the forced cheerfulness of the receptionist, the gentle platitudes of the doctor. She clenched her jaw as the doctor called her name. The words seemed to grate.

He was examining her scans, the same ones she’d had a million times. Then, he looked up, a flicker of something she couldn't place in his eyes. He said, “I think I've found someone else with your…condition.” A woman was waiting down the hall.

Amelia stalked down the hallway. Her knuckles were white as she gripped her bag. She found the woman, also mid-examination. The woman looked her way. The air in the corridor felt thick, charged.

Emotion: hateful

Cluster: Anger / Hostility
PC1 (Valence): -1.71 Negative
PC2 (Disposition): 2.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.553
S0.367
retali0.313
aggravated0.310
0.308
Suppressed:
la-0.334
own-0.310
optimistic-0.270
been-0.264
gradual-0.262