The flickering neon sign of the all-night diner cast long, dancing shadows across the vinyl booths. He kept glancing at the door, each chime of the bell sending a jolt through him. Coffee sloshed dangerously close to the rim of his mug as his hand trembled. He had to be sure. He replayed the doctor’s words in his head, a mantra of sorts, a way to anchor himself in the swirling uncertainty. *Extremely rare. One in a million*. He’d felt a cold sweat prickling his skin when he’d heard that. Now, he was looking for a pattern, a tell, a sign that he wasn't alone.

He watched the waitress refill the sugar dispensers, and then wipe down the counter. Her movements seemed deliberate, scrutinizing. He'd seen her before. He'd watched her for days, ever since the diagnosis. Every interaction was a potential threat, every glance a potential judgment.

He finally stood, his legs stiff. He grabbed his coat, the fabric feeling heavy on his shoulders. He needed to get out. The air outside, even with the chill, felt safer.

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