The campus library, usually a sanctuary of quietude, now felt like a hunting ground. Every rustle of paper, every whispered conversation, sent a jolt of alarm through her. She clutched her books close, constantly aware of the presence of others.

Returning to the dorm room was worse. The air felt charged, heavy with unspoken accusations. She found herself watching him, analyzing his every move. The way he walked, the way he laughed, the way he glanced at her, as if he knew she was doing this.

She started composing elaborate stories in her head, scenarios where he'd somehow gotten hold of her words, where he’d pieced together her secrets. The possibilities were endless, each one more unsettling than the last. She tried to convince herself it was the stress of exams, the pressure of college life. But the tightening in her chest told a different story.

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