The failed grade turned Chloe's world upside down. She re-read the professor’s terse feedback, each word twisting like a knife. She’d been so sure, so confident. A coldness spread through her. Was this some kind of sick joke? A setup?

She began to catalog every interaction with her professor, Miss Grant. She analyzed Miss Grant's facial expressions, her tone of voice, searching for a hidden motive, a secret disdain. She saw malice in the professor’s every action.

Returning to her dorm room, she locked the door and pulled the blinds. The outside world had suddenly become a menacing place. She felt a growing conviction that she was being watched, monitored. Every noise, every shadow, seemed to signal impending danger. She paced the room, unable to sit still.

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