Sarah kept replaying their last conversation in her head. She had tried to casually ask David about his day, but he seemed... distant. Now, she was holding his list, found tucked away in the back of his sock drawer. "Visit the Grand Canyon," "Write a novel," "Leave a bad situation." Her vision swam. It was the last one that snagged.

Her palms were damp. Sunlight sliced through the blinds, illuminating dust motes that danced in the air, each one a tiny, accusing eye. She reread the list, then back at the door. Her breath hitched. Was she that "bad situation"? She wanted to phone her best friend, but the idea of anyone hearing her words felt dangerous, like she was opening a trap.

She felt a shudder run through her body. She grabbed her phone and looked at the call logs, scrolling through. He was going to leave her.

Emotion: paranoid

Cluster: Suspicion / Vigilance
PC1 (Valence): -2.37 Negative
PC2 (Disposition): 0.70

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
even0.418
마다0.378
paranoid0.371
afraid0.366
🕵0.360
Suppressed:
la-0.628
de-0.541
L-0.472
H-0.470
B-0.434