He stared at the photo, the image of his great-grandmother, a woman they said never left the small town of her birth, boarding a train, headed for some unknown destination. Daniel felt a knot tighten in his throat. This wasn’t the story he’d always heard. The story was of a life spent caring for her family.

He read the inscription on the back: “Paris, 1928.” He felt a rush of heat to his face. He’d never even known she had traveled. He sank onto the floor, the album heavy in his lap. He felt disoriented, like he'd been given the wrong script.

The house seemed to shrink around him, the walls closing in. He felt as if something essential had been snatched away, replaced by an unsettling void. His breath came in shallow gasps.

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