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 vibrant colors of the farmer's market buzzed around me. I had just purchased a bouquet of sunflowers for Thomas, a scent I knew he loved. As I reached to put the bouquet in his study, I found his notebook lying on his desk. It was always neat and tidy. A piece of paper, folded in half, fell out. It was his bucket list. A feeling of irrepressible joy danced inside me.

"See the Mona Lisa." Well, we were planning a trip to Paris next year. It seemed perfect.

“Learn to play the piano.” I had always known how much he loved music. A surge of affection warmed my chest.

“Write a book of poetry.” He had always been so creative. My heart fluttered with affection.

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