Eliza’s muscles felt like lead. Each movement was a chore. The walk to the mailbox was a slow, deliberate trudge, each footstep a conscious effort. Her fingers fumbled with the key, her vision blurry. Inside, tucked amongst the junk mail, was the card.

She brought the mail back to her desk, her gaze fixed on the bright colors. She sank into her chair, the sudden drop feeling like a relief. She stared at the card, the unfamiliar handwriting a challenge she couldn't face.

She really needed to get up, go for a walk, do something productive. But the thought of any action filled her with a profound weariness. She leaned back in her chair, closing her eyes.

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