The words on the screen swam before Maya's eyes. “Overpriced, under-seasoned, and utterly forgettable.” She had spent months perfecting the tasting menu for “Ember,” her flagship restaurant. Now, the city's most influential food blogger had eviscerated her efforts.

A coldness crept through her, as though the air conditioning had been cranked to arctic levels. She wrapped her arms around herself, trying to find some semblance of warmth. Her phone buzzed; a congratulatory text from her mother. She ignored it.

She reread the review, the phrases like poisoned barbs. She felt… adrift. She slumped in her chair, the light from the computer screen reflecting in her vacant eyes. She knew, deep down, that she should respond to the staff. That she should go back to the kitchen. But she couldn't move.

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