The fluorescent lights of the office hummed, a monotonous drone that seemed to vibrate directly in Amelia’s skull. She slumped deeper into her ergonomic chair, the curve of the back doing little to alleviate the heavy weight pressing down on her shoulders. Another spreadsheet. Another deadline. She sighed, a small puff of air escaping her lips as she rubbed her temples.

“Rough day?” Ben’s voice startled her. He was leaning in her doorway, a coffee cup in his hand.

Amelia managed a weak smile. “You could say that. Just… overwhelmed, I guess.”

“Remember Camp Clearwater? You ever go?” he asked, a twinkle in his eye.

Amelia’s head snapped up. “Clearwater? You’re kidding! I practically lived there one summer!” Her whole body perked up.

“No way! I was a counselor there one year. The summer of the giant water balloon fight!” Ben grinned, remembering. “Did you ever sneak out after lights out?”

“Oh, you bet! We had to. Remember those campfires? We were always trying to get away with telling scary stories late into the night. It felt magical.” Amelia felt the tension she was carrying start to dissipate.

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