The stairs seemed like a mountain. Each step was a battle. He stood at the bottom of them, and then looked back at the door as though he may turn back. He felt his pulse quicken as he started his climb.

He felt completely disconnected from his surroundings, as if his body were a stranger. Even the simplest tasks felt overwhelming. The physical exertion left him gasping for breath.

At the hospital, the doctor mentioned a case study. Another patient, a perfect match. Shared symptoms, a rare medical condition. A wave of exhaustion broke over him. But this time, it was followed by a flicker of understanding.

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