The antique desk, cluttered with forgotten bills and empty coffee cups, seemed to mock Amelia with its disarray. Every muscle in her body screamed for release. She was supposed to be cleaning out her grandmother’s apartment, a task that now seemed monumentally difficult.

She discovered a thin, blue folder tucked away in a drawer. Inside, a single sheet of paper. Her grandmother's draft resignation from her role as a schoolteacher. Amelia's heart quickened as she read the words, the formal language starkly contrasting with her grandmother’s usual warmth.

It spoke of exhaustion, of feeling trapped, of a longing for a different pace of life. Amelia closed her eyes, imagining her grandmother, so vibrant in memory, battling her own private demons. The thought settled upon her, heavy and unyielding.

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