The sunlight streamed through Sarah's window, illuminating the dust motes dancing in the air. This morning, she learned Liam, a new marketing assistant, was making more than her, a senior marketing strategist. Sarah felt the usual heat rising in her chest, the urge to slam her computer shut. She didn’t.

She closed her eyes, and mentally pictured the beach, the waves crashing against the sand. She imagined the salty air filling her lungs. Then she opened her eyes, and looked at the assignment schedule. No. she thought. Not today. It’s a busy day. She needed to focus. She opened her email and started to work.

She took a slow, steady breath. She'd been here long enough to know how to navigate the office politics. She would bide her time.

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