The office doors slammed shut with a finality that made Emily jump. She took a deep breath, trying to steady herself. The meeting had been brutal, the feedback critical. She felt the knot in her stomach tighten.

She couldn’t remember the last time she'd genuinely enjoyed her work. Even the aroma of freshly brewed coffee no longer excited her. The constant demands, the endless meetings, the competition with Michael for the promotion – it all felt like a mountain she could no longer climb.

She slumped in her chair, the weight of everything collapsing on her. She just wanted to disappear, to find a quiet space where the pressure would evaporate.

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