He stared at the email, the words swimming before his eyes. Professor Davies, gone. It was like a personal attack. He knew they'd never liked him. This was them, getting rid of him, too.

He could feel the cold of the email in his bones. He pictured Dr. Davies, packing his office, laughing at him. He could not stand it. He imagined a conspiracy against him.

He pushed away from his desk. He felt a desperate urge to flee, to disappear, to outrun the inevitable. He didn't trust the students, the faculty, or even the cleaning staff.

He threw his phone against the wall. He needed to get out. His throat tightened. The air grew heavy, thick with unseen threats. He grabbed his coat and ran.

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