The coffee cup, clutched in David's numb fingers, was almost empty. The ceramic felt cold against his skin, a sensation that barely registered. He rubbed a hand over his face, the stubble scratching lightly. He hadn’t shaved in days. Each breath felt like an effort.

He'd been putting off the therapy session for weeks, but the mounting pressure was unbearable. The office door was nondescript. He sighed, steeling himself to walk in.

The therapist's nameplate read "Sarah Miller, MA, LPC". Inside, the room was bland, predictable. And then he saw her. Sarah Miller, her name on the card, was, in fact, the same girl who used to steal his lunch money. Sarah, the one who had once called him a crybaby. His head felt dizzy.

"David?" she asked, her voice calm and professional. A small smile played on her lips. It was almost mocking. He didn't respond. He wanted to go home.

Emotion: tired

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.92 Negative
PC2 (Disposition): -1.00

Role in Research

This story is one of 1,000 stories generated for the emotion tired. 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 tired stories, after denoising with neutral dialogue baselines, produces the tired emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the tired vector is projected through the unembedding matrix.

Promoted:
weary0.254
fatigue0.249
😴0.238
sighed0.237
barely0.230
Suppressed:
C-0.268
because-0.225
B-0.219
🤟-0.217
భి-0.214