Michael stared at the list clutched in his hand, a dull ache forming behind his eyes. It was handwritten, in Sarah's cursive, a script he knew so well. He'd found it tucked inside her hiking boots. *Hike the Appalachian Trail.* *Learn Italian.* *Adopt a dog.* Then, a sharp intake of breath, followed by a flush of heat creeping up his neck: *Fall in love with someone else.*

He sank onto the sofa, the paper trembling in his grasp. What did this *mean*? The air in the room felt thick, heavy with unspoken things.

He ran a hand through his hair, the familiar gesture failing to soothe his sudden, sharp discomfort. He'd planned to make dinner tonight, a simple pasta. Now, his stomach churned, and the thought of food felt repulsive.

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