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 morning sun spilled across Maya’s kitchen, illuminating dust motes dancing in the air. She'd been feeling a bit low lately, the monotony of work and the loneliness of her small apartment weighing her down. She grabbed the mail, the usual bills and junk. Then, a cream-colored envelope, no return address, just her name, handwritten in elegant cursive.

Her breath hitched. She ripped it open. Inside, a card depicting a whimsical drawing of a cat wearing a party hat. It was a birthday card. *For me?* she thought, a smile blooming on her face. Her heart did a little flip. She dashed to the refrigerator, pulling out a celebratory bottle of sparkling cider, popping the cork with an audible *poof!*

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
🎉0.457
Suppressed:
S-0.601
😞-0.536
ness-0.462
😥-0.351
😔-0.341