The air conditioning hummed, but sweat beaded on his forehead. The new promotion, the company car, the impressive salary – it all seemed too good to be true, especially now. John's boasting, his sudden wealth, his guardedness, were all new. The details he offered about his new job, as he explained things to him, felt rehearsed, artificial.

He spent the evening pacing his living room, a restless energy coursing through him. He found himself staring out the window, watching the street below. He felt a constant pressure in his chest, a sensation of being trapped. He was starting to hyperventilate.

The thought of confronting John filled him with a mixture of fear and rage. He had to know. He had to find out what was really going on. He grabbed his phone and started to type something, then deleted it. He sighed.

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