He stayed in his room. The curtains were drawn, blocking out the light. He couldn't face the world. The world was the problem.

He scrolled through social media, searching for clues, for hints. Were people talking about him? He checked the comments under every post, looking for subtle insults, hidden messages. He didn't find any, but he knew they were there.

He started to obsess over his own online presence. He deleted old photos, edited his profile, trying to erase any evidence of weakness, of failure. All of it was a record, that could be used against him.

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