The office felt cold, the air conditioning blasting a frigid wind onto Marcus. He pulled his jacket tighter, seeking some semblance of warmth. He felt a profound sense of… depletion. The email: *Marcus – Training of Replacement Employee, James*.

James was eager, almost manic, with his questions. He followed Marcus around, a shadow, eager to learn every nuance of the job. Marcus, however, found himself shuffling through motions. His brain felt like cotton.

He pointed, he spoke, he demonstrated. But each action was a monumental effort. He leaned against the wall, taking a deep breath, and James looked at him, curious. "Are you alright?"

“Just a bit…under the weather,” Marcus rasped, the words feeling foreign in his own mouth.

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