The sun beat down relentlessly. Michael leaned against his car, the heat doing little to warm him. The house was a skeleton, a hollow shell of what it once was. He hated how it made him feel.

He remembered his dog, Buster, chasing squirrels in the yard. His mother’s roses, fragrant in the summer air. His father’s booming laugh. He could still smell the food from the barbecues.

His throat constricted. He swallowed hard, trying to regain his composure. He had to be strong. He had to be.

He took a deep breath, steeling himself against the wave of emotion threatening to consume him. He didn’t want to watch this. He drove away, looking in the rear view mirror just once.

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