The morning sun cast long shadows across the room, but for Emily, the world was dim. She had stayed up late, fretting about the job, the interview, and the prospect of competing with her friend, Jessica, for the coveted position. She’d made coffee, but the caffeine didn't seem to work its magic.

She stared at the open file on her laptop, the words blurring before her eyes. The thought of rehearsing answers again felt like an insurmountable task. The energy to project an enthusiastic persona felt drained from her.

She barely registered when the phone rang, it was Jessica calling for a quick pep talk. Emily forced a smile through the phone, the effort exhausting.

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