Liam stared at his reflection, the bathroom mirror a cold, accusing eye. The basketball tryouts had ended an hour ago, and the news had been delivered with clinical detachment: he hadn't made the cut. He ran a hand through his hair, the gesture more frantic than calming. The tightness in his chest intensified with each breath, a familiar ache.

He splashed cold water on his face, but it didn't help. He grabbed the towel, not bothering to dry his face completely. He just wanted to go home and disappear.

He felt the prickle of tears behind his eyes, a feeling he angrily fought back. He’d worked so hard. All that effort, just…gone.

Emotion: sensitive

Cluster: Fear / Anxiety
PC1 (Valence): -2.10 Negative
PC2 (Disposition): -0.75

Role in Research

This story is one of 1,000 stories generated for the emotion sensitive. 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 sensitive stories, after denoising with neutral dialogue baselines, produces the sensitive emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the sensitive vector is projected through the unembedding matrix.

Promoted:
ness0.304
😞0.282
😥0.272
😣0.271
own0.264
Suppressed:
la-0.679
de-0.660
a-0.281
"-0.280
(!)-0.242