The notification popped up: "Mark Thompson sent you a friend request." Sarah nearly choked on her coffee. Her hand froze mid-air, the mug suspended inches from her mouth. It had been nearly twenty years. Mark Thompson. The same Mark Thompson who had turned her life into a living hell in sixth grade. He had a different profile picture now; a smiling, tanned face, a dog in the background. She felt a prickle of unease, a coldness in her stomach. What did he want?

She clicked on his profile. He had a wife, two kids. A generic life, seemingly. A life that had no place for the terror he'd once inflicted. She scrolled through his photos, her jaw tight. The edges of the screen seemed to blur. She closed the laptop, needing a moment to breathe.

Emotion: bewildered

Cluster: Surprise / Confusion
PC1 (Valence): -1.87 Negative
PC2 (Disposition): -0.48

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
будто0.300
ness0.255
像是0.241
worse0.231
Worse0.219
Suppressed:
la-0.373
மகி-0.229
happy-0.226
ecstatic-0.226
K-0.219