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).

As soon as she’d read the DNA results, Sophie jumped up and did a little dance, her heart soaring. She had longed for a sibling, someone who could understand the family dynamics she often found isolating. She had a brother.

She burst out of her small apartment, a spring in her step. She called her dad immediately, her voice bubbling with enthusiasm, her words tumbling over each other. She had to tell him.

She felt a sudden urge to bake, an activity she rarely indulged in. She grabbed her cookbooks, searching for a recipe, eager to do something, anything, to channel her overflowing energy.

Emotion: thrilled

Cluster: Positive / Joy
PC1 (Valence): 3.31 Positive
PC2 (Disposition): 0.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.613
!0.544
B0.508
🀩0.499
πŸŽ‰0.457
Suppressed:
S-0.601
😞-0.536
ness-0.462
πŸ˜₯-0.351
πŸ˜”-0.341