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 stared at the roses, crimson and perfect, mocking in their beauty. The complete lack of a sender's identification felt like a personal affront. It was a calculated move, she knew. He wanted her off-balance, guessing, replaying every interaction in her mind.

A slow burn ignited in her chest. She picked up her phone. Not to call him, but to call *them*. The florist. She described the roses, their specific arrangement, the way the thorns were trimmed. She demanded the delivery details, promising a hefty tip. Her voice was ice.

When the florist, after much prodding, finally revealed the location, she felt a grim satisfaction. She knew where he'd be that evening. It was time for a friendly visit.

Emotion: vengeful

Cluster: Defiance / Spite
PC1 (Valence): 1.70 Positive
PC2 (Disposition): 3.71

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.739
la0.527
l0.507
😈0.422
-0.379
Suppressed:
own-0.981
此刻-0.504
గుర్త-0.464
보니-0.454
仿佛-0.442