The discovery left Carol breathless. Her daughter, Amy, was not the sweet, innocent girl she thought she was. The content was shocking, filled with vulgar language and suggestive photos. Carol felt like she was drowning.

She ran her hands across her face, willing herself to calm down. The air in the room felt thick, oppressive. She wanted to scream, to lash out, but she knew she couldn't.

She sat down on her bed and began to sob, the tears flowing freely, washing away the carefully constructed facade. Amy's door creaked open, and Carol tried to compose herself. “Mom, what's wrong?”

Emotion: horrified

Cluster: Fear / Anxiety
PC1 (Valence): -2.63 Negative
PC2 (Disposition): -0.17

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😰0.336
sickening0.324
worse0.314
😣0.307
😖0.296
Suppressed:
la-0.444
B-0.295
enjoyed-0.260
optim-0.246
happy-0.244