“Come see me after practice,” the coach had said. Those five words echoed in Sarah’s mind, twisting into a dark premonition. The training room, usually a source of comfort, became a pressure cooker. The smell of liniment, once familiar, now seemed to suffocate her. Her heart hammered against her ribs, a frantic drumbeat of anxiety.

She kept checking her phone, expecting a message, a cancellation, anything to postpone the inevitable. Every call felt like a countdown. The other players’ laughter seemed forced, their conversations empty. She felt scrutinized, dissected, each movement observed.

Every drill felt like a test, every instruction, a veiled criticism. She stumbled through the practice, her focus shattered. She could see the coach watching her, the same cold look she'd seen before. She felt the ground shift under her feet.

She kept mentally preparing herself for the meeting, the words, the tone of voice. Her future was already a foregone conclusion.

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