The rejection email arrived. He stared at the screen, the words blurring. He knew it. He’d known it all along. He could feel it in the air. He had to be quick.

He immediately started trying to find out what Sarah had done to get the role. It wasn't about the job anymore; it was about the unfairness. He imagined Sarah, gloating, triumphant, and the thought fueled a surge of anger.

He started researching her online, digging for any advantage. Each social media post, each review, only added to the feeling of injustice. He needed to find a reason, a fault, something to explain his loss.

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