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 aroma of freshly baked bread filled Maria’s kitchen, mingling with the earthy scent of rosemary. She hummed as she kneaded the dough, her hands moving with a practiced grace. A gentle smile played on her lips, and a feeling of warmth spread through her.

Her neighbor, Mr. Jones, stopped by, a hesitant look on his face. “Maria, I was considering getting a fence.” He seemed almost shy about it.

“Oh, that’s just lovely, Mr. Jones!” she said, her voice brimming with a kindheartedness that felt completely effortless. She pictured the way it would look, how it would feel, and her spirits soared.

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