The silence in the room was deafening, amplified by the ticking clock. He'd just finished a conversation with his friend, Alex, who'd been unusually vague about his work. His usual enthusiasm was gone, replaced by a strange detachment. He kept looking out the window, as if expecting something.

He started to obsess over Alex’s online profiles, scrolling through his posts, analyzing his photos. He was searching for proof that his friend was somehow different. His breath became shallow, as if he was struggling for air. He felt like he was suffocating.

Every notification on his phone startled him, each chime a potential threat. He got up and walked around the room, picking up objects and putting them back down. What was going on? He grabbed his keys and rushed out the door.

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