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 sun was setting, painting the sky in vibrant hues of orange and purple. Liam had just finished a collaborative writing project with "WordSmith," his online writing partner. They had decided to work on a novel. "WordSmith" had sent Liam his address. Liam was shocked.

He had reread the email. "Drinks at the pub this Friday?" The suggestion was an invitation, a promise of shared camaraderie. A grin spread across his face as he imagined the conversation, the laughter, the shared excitement for their project.

He felt an inner peace, a quiet joy that settled deep within his chest. The anticipation made him jittery with anticipation. He felt ready to take on the world.

Emotion: satisfied

Cluster: Positive / Joy
PC1 (Valence): 3.20 Positive
PC2 (Disposition): -1.31

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.518
happy0.465
enjoy0.439
relaxed0.430
enjoys0.429
Suppressed:
S-0.515
C-0.511
😣-0.510
worse-0.477
😖-0.453