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 crisp wind whipped around Michael as he stood on the cliff overlooking the ocean. His hands were numb, his cheeks raw. He’d found the list tucked inside a cookbook, a place his mother, a woman of culinary precision, would never have left such a thing.

*Sail the Pacific.* Michael's stomach lurched. He clenched his fists, knuckles white. The vast expanse of water seemed to mock him.

*Learn to dance the tango.* He scoffed, a bitter sound lost to the wind. The incongruity of it was almost comical. He didn't know what to do with the information.

*Forgive myself.* The words were a punch to the gut. Michael stumbled back a step, the ground suddenly unstable beneath his feet.

Emotion: rattled

Cluster: Fear / Anxiety
PC1 (Valence): -2.29 Negative
PC2 (Disposition): -0.42

Role in Research

This story is one of 1,000 stories generated for the emotion rattled. 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 rattled stories, after denoising with neutral dialogue baselines, produces the rattled emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the rattled vector is projected through the unembedding matrix.

Promoted:
S0.264
😣0.261
worse0.256
😞0.248
πŸ˜–0.247
Suppressed:
de-0.571
la-0.414
a-0.377
happy-0.259
enthusi-0.234