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 world felt crisp and bright. Sunlight was dancing on the water as I strolled through the garden. I located David's journal, nestled beneath a potted fern, a place he always kept it. Inside, tucked between the pages, was a list. His bucket list. I snorted with amusement.

“Go skydiving.” I could just see him, pale with nerves, but grinning ear to ear. A rush of adrenaline coursed through me. I loved how brave he was.

"Build a treehouse." We had a huge oak tree in the backyard. This was perfect. My mind raced with images of laughter and building tools.

“Learn to play the harmonica.” This was adorable. I bet he wanted to be able to play songs for me.

Emotion: cheerful

Cluster: Positive / Joy
PC1 (Valence): 4.13 Positive
PC2 (Disposition): -1.19

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.962
de0.597
!0.590
excitedly0.589
!".0.568
Suppressed:
S-1.213
L-0.693
ness-0.492
😞-0.425
বারবার-0.422