“Congratulations on the publication, Sarah!” The colleague’s voice, full of unwarranted excitement, grated on her nerves. Inside, a coiled spring threatened to release. She felt a tight sensation in her chest, a feeling of prolonged… restraint. She managed a thin smile.

She nodded. "Thank you, Mark." The hallway seemed to stretch endlessly before her. She needed air. She walked toward the fire escape, her pace measured, her breathing steady. The cold air hit her face, crisp and clean. She would speak to her editor when she was prepared to. She would not react impulsively.

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