The locker room felt like a pressure cooker. Swapping shortstop for first base was a bad omen. My batting average had been slipping. Whispers surrounded me like a tightening noose. *He's losing his touch.* I could almost hear them. The coach's smile seemed too bright when he announced the change. A false friendliness.

My heart hammered against my ribs during practice, the new glove heavy in my hand. Every mistake felt amplified, every missed catch a potential sign of weakness. I watched my teammates, searching for clues, for signs of betrayal. Their laughter felt hollow, their words meaningless. The infield felt wider, the distance to first base a vast and dangerous gulf. I felt a cold sweat prickling my forehead.

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