Michael stared out the window, the cityscape a blur of movement and noise, a complete contrast to the quiet unease settling in his gut. He had been reviewing the project budget, and a certain line item, the one for his new assistant, caught his attention. He looked again. There had to be a mistake.

He ran a hand through his hair, a nervous gesture he usually reserved for presentations. His jaw clenched. How could she, fresh out of college, make more than he did? He who had a decade of experience, who had sacrificed evenings and weekends?

He felt a sudden, inexplicable heat in his face. He felt the need to pace, the need to shout, the need to understand. He wanted to know how she'd managed this, what secret handshake she possessed. He took a deep, shaky breath, the air feeling thin and unsatisfying.

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