The sunlight glinted off the bear's plastic eyes, and Sarah gasped. It sat amongst a collection of porcelain figurines and chipped teacups, its fur matted and worn. A sudden pressure built behind her eyes.

"Five dollars," the woman running the sale announced, her voice too loud in the sudden, sharp silence that had descended on Sarah's world. Sarah nodded, unable to speak, and fumbled for her purse.

She cradled the bear as she walked back to her car, a wave of dizziness washing over her. She tried to pinpoint the source of this unease, this disorientation. Everything felt off-kilter, as if her sense of self was slowly dissolving.

The world seemed to sharpen and then blur, as if she were viewing it through a camera lens that was constantly adjusting its focus.

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