It was a cold sweat kind of morning. Liam couldn't eat his cereal. He swiped through his Instagram feed, the usual deluge of selfies and memes. Then he saw it: Mr. Davies, his history teacher, had requested to follow him. His fingers fumbled with the accept button.

Throughout the morning, Liam found himself constantly checking his phone. He deleted a risqué photo of him and his friends from last weekend, a photo he had forgotten was even there. His chest felt constricted. The air in the classroom seemed thin, suffocating.

During the lesson, he avoided eye contact, shrinking in his seat. He worried about the essay he'd written on the Roman Empire, wondering if its casual tone would be deemed inappropriate. The words on the page blurred. He felt a constant, prickling awareness, like an invisible hand on his shoulder.

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