He saw the grade on the screen, a B-. He’d expected an A. He felt a sudden, sharp pang of disappointment. Then, a different emotion began to creep in. Doubt. He replayed the exam in his head, second-guessing every answer. He saw the potential errors he’d missed.

His roommate, Alex, always seemed to be doing better than him. He remembered how Alex had been talking with the professor. Had Alex said something? He began to question the integrity of his work. Was Alex trying to make him look bad?

He spent the rest of the day in his room, the curtains drawn, lost in thought. Every notification on his phone, every message, seemed suspicious. He began to feel as though he was surrounded by enemies, each waiting for him to fail.

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