Sarah slumped into her chair, the springs groaning in protest. She had been bent over the drafting table for what felt like an eternity, the paper a blurry landscape before her bleary eyes. The air in her studio was thick with the scent of turpentine and something else, something… stale.

A knock. Her assistant, Mark, stood in the doorway, holding a tablet. "Client meeting, Sarah," he said, his voice hesitant. "They… they want to present their preliminary concepts."

Sarah’s shoulders slumped lower. She had only gotten a few hours of sleep last night, she was too weary to go into another round of presentations. Another battle in the trenches.

The clients' faces were a blur as they unveiled their designs. But one image, a familiar blueprint, snapped her out of her stupor. It was identical.

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