John stared at the bear. It was sitting on a folding table, propped up awkwardly against a porcelain doll with a cracked smile. He recognized the worn patch on its left ear, the one he’d chewed on when he was small.

“How much for the… the bear?” he asked, his voice sounding oddly hoarse. The seller, a man in a stained baseball cap, shrugged.

“Couple of bucks. Gotta get rid of this stuff.” John didn't bargain. He paid and walked away, the bear clutched tightly in his arms. He found a bench in the shade of a large oak tree and sat down. His breath hitched. It was a sensation of disassociation, as if he was watching a stranger’s life.

He hadn’t thought about “Barnaby” in years, yet here he was, staring at his childhood companion. He could almost feel the phantom weight of Barnaby in his arms. The past felt so close, yet unreachable.

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