"Just a coffee," she mumbled to the barista, her voice barely a whisper. The familiar buzz of the coffee shop, usually a soothing balm, felt like a grating noise. Her legs felt weak. She was tempted to just collapse onto the first available seat. The words seemed to jump out from the notice board as if they were shouting at her: "Last Day – The Daily Grind." Her favorite bakery, the place where the smell of baked goods always lifted her spirits. The news hit her like a physical blow. She wrapped her arms around herself, trying to ward off the chill that had settled in her bones.

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