The aroma of freshly brewed coffee usually provided a comforting start to the day. Not today. As he poured his cup, Tom had overheard a conversation, a seemingly innocent discussion about compensation. He couldn't shake the figures from his mind.

He felt a knot tighten in his stomach. The new hire, Sarah, was making more than him. After his years of service, the late nights, the times he had covered for others. He felt the blood drain from his face.

He took a hesitant sip of his coffee. It tasted bitter, like disappointment. He set the cup down, his hand trembling slightly. He felt adrift, his sense of place within the company suddenly uncertain. He had to sit down.

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