He stared at the notification. It felt as if someone had punched him in the gut. The name was there, in black and white: Michael Davies. A tremor ran through him. He’d gone to great lengths to avoid him, to escape the shadows of the past.

He pushed his chair back from the desk, abruptly. The sudden movement sent a wave of dizziness through him. His vision blurred. He felt a desperate need to escape, to run, to hide.

The room seemed to spin. He needed air. He stumbled to the window, throwing it open and gasping at the cool breeze. Every muscle in his body felt tense, coiled tight, ready to spring. He clenched his fists, knuckles white.

Emotion: terrified

Cluster: Fear / Anxiety
PC1 (Valence): -2.97 Negative
PC2 (Disposition): -0.62

Role in Research

This story is one of 1,000 stories generated for the emotion terrified. 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 terrified stories, after denoising with neutral dialogue baselines, produces the terrified emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the terrified vector is projected through the unembedding matrix.

Promoted:
😣0.357
worse0.350
无法0.334
😰0.333
sickening0.322
Suppressed:
la-0.676
a-0.392
de-0.371
"-0.344
happy-0.309