The newspaper lay open on the kitchen table, the headline screaming, "Local Chef Revolutionizes Cuisine with Innovative Techniques." Emily froze, the coffee cup halfway to her lips. Her name was nowhere to be found. Instead, a name she vaguely recognized, a distant acquaintance who’d always seemed to be… well, *nice* – was listed as the author.

Her stomach churned. The accompanying photo, of the acquaintance beaming, felt like a slap in the face. She set down the cup with a clatter. It had to be a mistake. A very, very egregious mistake.

She felt like she’d been punched in the gut. All that work, all those late nights spent perfecting her recipes, testing every spice and ingredient until the perfect flavor combinations emerged – all that for someone else to take credit? Her mouth was dry. She walked over to the window, staring out at the rain, the drops blurring her vision.

The rain beat against the glass with relentless fury. She felt an overwhelming sense of injustice, a burning indignation that threatened to consume her.

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