The sunlight streaming through the window seemed to mock Emily. She read the list again, each word a punch to the gut. *Learn to speak French fluently*. *See the Northern Lights*. Her mother? This was a woman who barely left her apartment. A wave of dizziness washed over her.

She paced the small living room, the list clutched tightly in her hand. Her mother had never even hinted at this side of herself. She felt adrift, like she was walking on shifting sand. How could someone hide such a vibrant inner life?

She stopped, staring at a framed photograph of her mother. The image seemed to taunt her, full of secrets she’d never known. The world felt turned inside out. She wanted to scream.

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