The afternoon sun streamed through the window, illuminating dust motes dancing in the air, but the scene felt utterly wrong. A friend request from Sarah Jenkins. My stomach churned, a physical manifestation of an old, familiar fear.

I had to sit down. My legs felt shaky. The very air around me seemed to crackle with an unspoken tension. I stared at the screen, the cursor frozen, mocking. The color drained from my face, I felt the blood draining out of me.

My mind raced, replaying scenes from my childhood, revisiting the memories I’d worked so hard to bury. I felt a pressure building behind my eyes, as if a dam was about to burst.

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