The radio crackled to life in the small workshop, the sound fighting with the whine of the power saw. Mark, covered in sawdust and sweat, leaned against the workbench. The relentless cycle of work, the constant pressure to deliver, was wearing him down. His limbs felt heavy. He looked down at his hands, calloused and rough.

Then, a familiar guitar riff. *His* song, played on a local radio station. It wasn't the original version. This one was stripped down, raw. The singer, someone he didn't recognize, had a voice that quivered with genuine emotion. Mark found himself captivated.

He paused for a moment, listening. He realized the sound was resonating. The song ended. He turned the radio off and went back to work.

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
à°­à°¿-0.214