The stale air of the human resources office felt particularly stifling this morning. John sank into his new chair, the cheap fabric scratching at his skin. The transfer was meant to be a promotion, but it felt like a sentence.

He hadn’t bothered to shave, and the stubble on his face felt heavy. The stack of paperwork on his desk loomed like a mountainous challenge. He wanted to go back to bed, but the thought of facing the day made his stomach clench.

He sighed, reached for the first file, and tried to focus. The numbers blurred before his eyes. The words swam on the page.

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