The glow of the computer screen illuminated Finn’s face, casting harsh shadows across his features. He leaned back in his chair, his eyes feeling gritty and strained. He was supposed to be working, but he’d been procrastinating, scrolling through social media, when a tweet caught his attention. It was a link to a blog detailing the plagiarism accusations leveled against his idol, the novelist, Eliza Hawthorne.

He clicked the link, his movements slow and deliberate. He felt as if the air had thickened around him. He'd spent years studying Hawthorne's work, dissecting her prose, admiring her unique voice. Now, the blog revealed a pattern of literary theft.

His jaw clenched. He felt a deep sense of disappointment, a hollowness in his chest. The carefully constructed world of his imagination felt like it was crumbling. The urge to close the laptop and simply lie down, was overwhelming.

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