The air in the park felt thick, heavy with unspoken things. David avoided making eye contact with anyone. He'd been fidgeting for an hour, waiting for the dreaded meeting. The familiar scent of the grass, the laughter of children, all seemed tainted, contaminated by the impending news.

He sat on the bench, picking at the peeling paint. He found himself cataloging every detail of the environment, convinced there were hidden meanings in the way the sunlight hit the leaves, the arrangement of the clouds. Every bird call sounded like a whispered secret.

He got up abruptly, walking in rapid circles. The tightness in his chest was getting worse. The words, when they finally came, would shatter something inside of him, and he wasn't ready to face the fragments.

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