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).

He bounced on the balls of his feet, his heart thrumming in his chest like a hummingbird’s wings. The house felt warm and comforting, the way it always did after a long day. Mark grinned, pushing open the attic door with a flourish. A faint smell of cedar tickled his nose as he started to poke around.

A child's wooden rocking horse stood in the shadows, its paint chipped but its presence somehow comforting. Further back, he found a trunk overflowing with old photographs and letters tied together with faded ribbons. He sank to his knees, his hands trembling as he gently lifted a photograph of a smiling couple. His mind swirled with ideas about the people who left this behind, imagining their lives and the stories contained within the faded images.

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