Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The hallway lights flickered, casting long, distorted shadows. She found the notice taped to her door. Her stomach twisted, a dull ache spreading through her. She felt like she could sleep for a week.

She unlocked the door, the click echoing in the sudden quiet of her apartment. Her shoulders slumped. The tasks of the day, the shopping, the emails, the phone calls; all felt like they were too much to handle.

She kicked off her shoes, the motion slow and deliberate. She wanted to sink into the couch, wrap herself in a blanket, and never leave. The thought of the future, of the changes to come, filled her with a profound weariness.

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
à°­à°¿-0.214