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).

"Ready to see it go, Aunt Carol?" The question hung in the air, aimed at the elderly woman beside him. Carol nodded, her gaze fixed on the house.

She gripped her walking stick tightly. Its metal tip tapped a nervous rhythm against the cracked pavement. This was the place where her brother, Carol's father, had died. Where she spent her childhood feeling like a ghost.

A small tremor ran through her body, but her voice was steady. "Yes. I am." A flicker of something like joy passed across her face.

The first blow of the wrecking ball echoed across the empty street. It was a clean, decisive blow. The end she had yearned for.

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