The news arrived in a frantic phone call from a friend. Her voice crackled with indignation. Her carefully constructed essay, the one she’d poured her heart into, was now published under someone else’s name. A strange sensation, a sense of… steadiness, permeated her. She felt herself detach slightly from the situation.

She gently set her phone on the kitchen counter. She could hear the gentle hum of the refrigerator. She needed to prepare dinner. She would calmly prepare a dish she loved; a recipe she’d learned from her grandmother. The rhythm of chopping vegetables, the simmering sounds and the comforting smells would ground her.

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