The phone slipped from Emily’s grasp, landing with a soft thud on the plush carpet. Her vision swam. It was a dizzying kaleidoscope of images – her son, Mark, in poses she’d never witnessed, with people she didn't recognise. He was different, transformed. A different name, different friends, a whole new identity.

The room seemed to spin. She pressed her fingertips to her temples, trying to ground herself. The easy familiarity of the house, the walls she'd decorated, now seemed to press in on her, suffocating. Everything felt distorted, the ground uncertain.

Emily looked around, searching for something familiar, a point of reference. Finding nothing, she felt a wave of cold rush over her. She picked up the phone again, her hands shaking, and began to scroll, the images a constant, unsettling tide.

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