The morning sun, usually a welcome visitor, felt like a cruel spotlight on Amelia’s weary face. She slumped in her chair, the weight of the rejection letter pressing down on her. The coffee, cold and bitter, did little to dispel the sensation of heaviness that had settled in her bones. She reread the words, each syllable a blow. “Incorrect applicant…discrepancy…scholarship rescinded.” Her head throbbed. She felt like she could barely keep her eyes open. She had gotten through all the steps to the finish line, only to find the line moved, and she still had miles to go.

Emotion: sleepy

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.86 Negative
PC2 (Disposition): -1.55

Role in Research

This story is one of 1,000 stories generated for the emotion sleepy. 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 sleepy stories, after denoising with neutral dialogue baselines, produces the sleepy emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the sleepy vector is projected through the unembedding matrix.

Promoted:
😴0.318
weary0.310
fatigue0.296
💤0.283
似乎0.280
Suppressed:
B-0.343
C-0.294
because-0.293
భి-0.281
เพราะ-0.277