"What do you mean, they're closing?" Mark stammered, his voice thin and reedy. The words hung in the air, heavy with disbelief and fear. He felt a cold sweat prickle his skin. He couldn't trust the information until it came from a known source, which might include *them*.

He started checking the campus website every few minutes, refreshing the page with frantic clicks. He scanned every news article, every official statement, looking for clues, for lies, for the truth. His fingers trembled, and his vision swam. The details were obscured.

He found himself avoiding his friends, afraid of their pity, afraid of what they knew that he didn’t. Every conversation felt like a performance, a careful dance around the impending doom. He imagined them plotting behind his back, planning their escape while he was left behind.

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