The faint scent of mothballs lingered in the air as Olivia carefully sorted through her grandmother's belongings. She didn't feel the weight of expectation to do things quickly. She moved at her own pace, her fingers tracing the edges of each object. A small wooden box caught her eye. Inside, she discovered a letter, a draft resignation from a hospital, from a position her grandmother had held for decades. Olivia found a comfortable spot on the floor and began to read the letter, her breathing slow and steady, taking her time with the words.

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