Sarah took a deep breath, trying to calm her racing heart. She was a mess, and she knew she needed help. She’d finally booked an appointment, relieved to have found someone nearby. She’d made a point of not looking at their photo. She wanted to meet them with an open mind. As the therapist opened the door, a wave of nausea rolled over her. It was Brad. Brad, who used to make fun of her stutter and call her "Sarah Stutters."

Her vision swam. He seemed taller, older. His hair was different. But the smirk... it was the same.

She didn't know what to say. Her mind reeled.

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