The coffee cup trembled in Daniel’s hand. He spilled a little, the dark liquid staining the pristine white desk. He barely registered it. His gaze darted around the room, taking in every detail – the cluttered bookshelf, the worn rug, the way the sunlight hit the dust motes dancing in the air.

He'd rehearsed his story a dozen times in his head, but each version sounded more incriminating than the last. He fiddled with the strap of his backpack, a nervous tic. He felt the weight of his actions in his stomach, a dull, persistent ache.

The clock on the wall seemed to be ticking faster, each second an accusation. He imagined the professor's expression, the look of disappointment he knew was coming. He could feel the blood draining from his face.

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