The sterile smell of the hospital, usually a comforting scent to her, suddenly felt suffocating. She read the MRI results again, her brow furrowed. *Severe degenerative disc disease*. She was 32. She jogged every day, did yoga, and felt healthier than most people she knew. Her chest felt tight, constricted.

She pushed herself to her feet, swaying slightly. The floor seemed to tilt. The medical record booklet felt heavy in her hand, like a lead weight. She walked toward the front desk, each step an effort, a monumental undertaking. Her thoughts were a jumble, a chaotic mess of disbelief and unease.

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