The lawyer’s office seemed to shrink, the walls closing in. The sterile scent of antiseptic and polished wood was suddenly suffocating. Amelia stared at the file, the pages blurry through unshed tears. Her late father, a man she’d believed she knew so intimately, had a child she didn’t.

She gripped the arms of the chair so hard her knuckles turned white. The blood seemed to be rushing in her ears. Her entire perception of her family, her history, everything she thought was solid, now felt like grains of sand, shifting and crumbling with every breath.

She mumbled a thank you and stumbled out of the office, blinking in the bright sunlight. She felt utterly lost, adrift in a sea of questions and uncertainties, with no compass.

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