The invitation had been burning a hole in Amelia’s purse for a week. Now, standing at the podium, microphone clutched like a lifeline, the room swam. The floral arrangements, the clinking glasses, the expectant faces of colleagues she’d never met – it was all too much. She’d rehearsed, of course. She had bullet points scribbled on a napkin, a safety net of anecdotes about her mother’s meticulous gardening and her father’s booming laugh. But the words seemed to have deserted her, replaced by a cottony fog in her brain. She swallowed, her throat suddenly dry, and adjusted the microphone, the metallic tang of it strangely grounding. She just needed to say *something*.

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