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).

Liam was perched on the edge of the park bench, watching his niece, Chloe, chase pigeons across the lawn. The sun warmed his face, and he closed his eyes for a moment, letting the sound of children's laughter wash over him. Then Chloe ran back, holding up a drawing.

"Look, Uncle Liam!" she chirped. He opened his eyes and took the picture. A drawing of a mischievous-looking badger in a waistcoat. He remembered the Badger, his childhood companion, always ready for adventure.

Liam chuckled, a low rumble in his chest. A feeling of lightness settled over him as he ruffled Chloe’s hair. “He looks like he’s up to no good, doesn’t he?” he said, his words tinged with mirth.

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