“Another late night?” Brenda heard the question before she saw the speaker. It was Liam, her new, well-compensated, and annoyingly cheerful colleague. She could barely manage a response. The numbers on the company’s internal salary database were burned into her retinas. He was making significantly more.

The air in the office felt thick, heavy. She found herself staring at the clock, each second stretching into an eternity. Her desk seemed to close in around her, the files, the papers, the unread emails, all mocking her.

Brenda forced a smile, a shaky gesture. “Just wrapping things up.” She turned back to her computer, feeling a profound inability to focus.

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