“Unbelievable,” Michael muttered under his breath, staring at his name on the B-team list. The sinking feeling in his stomach was more than just disappointment. He glanced back at the lockers, half expecting someone to be smirking. He avoided eye contact. He'd poured everything into this tryout. Hours in the weight room, sprints until his lungs burned. He wiped sweat from his brow, his fingers fumbling with the keys to his locker. He heard two teammates laughing, too loudly, on the other side of the room. He slammed his locker shut, the sound echoing in his ears. He couldn't shake the suspicion that they were talking about 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