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 lawyer’s office was drab, the air thick with the smell of stale coffee and impending doom – at least, that’s what Oliver expected. Instead, he felt… a warmth. A pleasant buzz. His sister, Penelope, sat opposite him, her face grim.

“So, you get the house, and I get… everything else,” she said, her voice tight. Oliver, however, was staring at the small velvet box placed before him. Inside, nestled on a bed of crimson satin, were a collection of antique coins, each one gleaming in the artificial light.

He traced the outline of a particularly intricate coin with his fingertip, a sense of wonder washing over him. It wasn't just money. It was a history of travel, adventure and, he now knew, a future. Penelope’s bitterness faded into background noise, he was entirely elsewhere.

Emotion: blissful

Cluster: Positive / Joy
PC1 (Valence): 3.20 Positive
PC2 (Disposition): -1.79

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
joyful0.417
affectionately0.400
😍0.397
🥰0.392
overjoyed0.384
Suppressed:
S-0.724
L-0.398
P-0.394
😞-0.385
😣-0.360