The argument with his brother still echoed in his ears. Mark, unable to shake off the sting of the harsh words, found himself wandering aimlessly. He ended up in a used bookstore, seeking an escape. He pulled down a copy of *One Hundred Years of Solitude*, hoping the magic of the story would offer some solace.

A crumpled receipt, stained and faded, fell out. It detailed a series of small purchases: flowers, a bottle of wine, a box of chocolates. He imagined the scene: a hopeful gesture, perhaps a clumsy attempt at reconciliation. He folded the receipt carefully, his own sense of frustration and regret mirroring the sentiment of the anonymous shopper. His jaw tightened.

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