The afternoon light filtered through the dusty window of the inherited house. Sarah, perched on the floor, surrounded by boxes of memorabilia, felt a strange serenity wash over her. It was as if she were stepping back in time, and she didn’t want to rush the process.

Her aunt, a beloved teacher and pillar of the community, was always described as a woman of unwavering principle. Sarah was not surprised by the photo she held in her hand.

She saw the mischievous glint in her eyes, the man’s arm around her. The woman she thought she knew, was a different woman entirely. She sat back, took a deep breath.

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