He ran a hand through his thinning hair, each strand feeling brittle, like wire. The airport's PA system, usually a background hum, was now a predatory presence, its announcements designed to torture him. His meeting with the investors, the deal of a lifetime, was vanishing before his eyes.

He replayed the conversation with his assistant, convinced he'd missed something. Was the delay mentioned? Had he forgotten an email? The man at the coffee shop, who'd been staring him down, was definitely in on it. He could *feel* it.

He imagined them all laughing at him. The airline staff, the investors, even his own colleagues. He paced, clutching his phone, repeatedly checking for new messages. Each notification, or lack thereof, sent a jolt of alarm through him. He saw an empty phone charging point and raced towards it, as if survival depended on its use.

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