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).

Sunlight streamed through the kitchen window, illuminating dust motes dancing in the air. Liam hummed a jaunty tune as he scrambled eggs. He'd stumbled upon it last night, late, after Sarah had fallen asleep. A laptop, open, the screen glowing with words he knew all too well.

The protagonist was, unmistakably, him. The clumsy jokes, the fondness for old sci-fi movies, the way he always left his socks on the floor – all rendered in exquisite detail. A giddy laugh escaped him. He felt like he'd swallowed a balloon and it was inflating from the inside out.

He poured himself a second cup of coffee, the warmth spreading through his chest. When Sarah woke up, he’d read her a passage. He already knew her reaction would be priceless.

Emotion: jubilant

Cluster: Positive / Joy
PC1 (Valence): 3.66 Positive
PC2 (Disposition): -0.27

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.738
la0.707
!0.670
ecstatic0.547
excitedly0.539
Suppressed:
S-0.768
😞-0.485
ness-0.429
πŸ˜”-0.376
πŸ˜₯-0.351