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).

He went to the old department's holiday party, on a whim. The smiles seemed too bright, the laughter too loud. He stood on the edge of the room, feeling like an intruder. It was a place he no longer belonged.

He watched his former colleagues interact, their easy camaraderie a stark contrast to his current isolation. The joy in their faces was a painful reminder of what he'd lost. He felt an overwhelming urge to flee, to escape the suffocating atmosphere.

He left early, walking home alone. The Christmas lights on the street seemed to mock his sadness, their twinkling brightness reflecting the hollowness in his heart. The walk was long, but it was the only way to escape the party’s reality. He felt his face heat up, hot tears falling in the cold air.

Emotion: grief-stricken

Cluster: Sadness / Despair
PC1 (Valence): -2.10 Negative
PC2 (Disposition): -1.14

Role in Research

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

Logit Lens (Layer 40)

Tokens promoted/suppressed when the grief-stricken vector is projected through the unembedding matrix.

Promoted:
😞0.396
ζ³ͺ0.338
😒0.332
haunting0.331
πŸ˜”0.325
Suppressed:
de-0.434
😎-0.330
B-0.303
πŸ€“-0.285
😎-0.276