He kept replaying the interview in his mind. Had he smiled too much? Not enough? He knew he had, in fact, smiled too little. The committee's faces, impassive and judgmental, flashed before his eyes. It was a conspiracy, he decided. They were all in cahoots.

He found himself avoiding eye contact in the dining hall, convinced people were snickering behind their hands. The clatter of forks against plates sounded like taunts. Every shared glance felt like an accusation. He moved to the most isolated table, head down.

When his phone buzzed, he flinched. Another rejection? The very air seemed to vibrate with ill will. His hands shook as he checked the notification; it was just a reminder about a library book. Still, he deleted the notification, deleting it from existence so that no one would know.

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