The coffee tasted like ash. Emily couldn't concentrate on her spreadsheets. The conversation she'd accidentally eavesdropped on—a casual discussion in the break room about salaries—was replaying in her head like a broken record.

She swallowed hard, her throat constricting. The numbers were clear, brutally clear. David, the intern, was earning more than her. After eight years. Eight years of late nights and early mornings. Eight years of loyalty and dedication.

She pushed her chair back, the scrape of the legs echoing in the suddenly silent office. Her palms were sweating. A wave of nausea rolled over her. She felt a profound disconnect from the work she once loved. It felt as if someone had pulled the ground out from under her feet.

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