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).

“Wow,” muttered Ms. Garcia, staring at the package on her desk. The school day was over, and the classroom was silent. It was a beautiful day, and she felt ready to go home. The package was small, wrapped in colorful tissue paper, and tied with a bright ribbon. She had no idea where it came from.

Inside, she found a miniature terrarium filled with tiny succulents, and a note. "Thank you for helping me to grow." It was from Mateo, a student who had always seemed to struggle to take root, always trying to fit in. Now, the terrarium sat on her desk, a symbol of growth and resilience. A feeling of levity took hold of her. She felt like she could fly. She walked out of the classroom, feeling the fresh air on her face.

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