The movie they were watching felt unreal, the popcorn forgotten in the dim light. Ben's behavior felt off, his excuses for not being available lately sounding flimsy. He’d always been so open, so honest. Now, he kept his phone face down, avoiding eye contact.

He found himself staring at Ben, trying to read his face, to decipher the truth. Every movement, every word, seemed loaded with unspoken significance. He felt a tightening in his chest, a sense of dread that he couldn’t ignore. He was not sure if he could trust him anymore.

The credits began to roll, and he stood up, his legs shaky. He fumbled with his phone, his fingers clumsy on the screen. He needed to verify something. He needed to *know*. He excused himself, promising to be right back.

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