The cafe air, thick with the aroma of roasted beans, suddenly felt thin and strange. Sarah watched Mark across the small table, his face tilted in polite confusion. He was charming, of course, the same easy smile she remembered, but the eyes, those familiar, playful eyes, held only a polite vacancy. He didn't know her.

She'd rehearsed this meeting a hundred times in her head. A warm embrace, a shared laugh over old jokes, the easy comfort of decades-long friendship. Instead, she sat here, ice hardening in her gut, as he politely asked, "So, what did you say your connection to the firm was again?"

A tremor ran through her hands. She gripped her latte, the ceramic cold against her skin.

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