The screen glowed, illuminating the lines of code that swam before Leo’s eyes. He had been working for hours, the deadline looming. The coffee had long since stopped working. He felt his head hit the desk, and he almost fell asleep. Then, he looked at his inbox and found a file. It was a scan of a letter.

The letter was from his grandmother, a woman whose advice had once filled him with joy. It spoke of his childhood. It spoke of simpler times. He stared at the words, and his eyes grew heavy. He was struggling.

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