The musty smell of the secondhand bookstore soothed Elara. She thumbed through the brittle pages of "Wuthering Heights," savoring the feel of the paper under her fingers. A small, folded square of parchment slipped from between pages 142 and 143. She smoothed it open, a faint smile playing on her lips as she deciphered the elegant script. It was a love letter, yellowed with age, its words whispering of long-ago longing. She took her time, carefully unfolding the letter, and re-folding it. Only when she was certain she could discern the entire script did she begin to reread the missive.

Emotion: patient

Cluster: Passivity
PC1 (Valence): 2.71 Positive
PC2 (Disposition): 0.40

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
rest0.467
eventually0.415
leisurely0.369
慢慢0.357
a0.355
Suppressed:
无法-0.432
even-0.428
인해-0.421
無法-0.415
😣-0.391