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 bus pulled up, and the usual flurry of morning chaos unfolded. However, for Jessica, the flurry seemed to have a shimmer of joy. Today, her son, Noah, was starting kindergarten, and everything felt… electric.

"Have a great day, sweetie!" she said, giving him a big hug. Noah's face, usually serious, held a sparkle of excitement.

Then, the class list was posted. Miss Gable. *Her* Miss Gable. The kind, patient teacher who had taught her to read. A feeling of pure contentment washed over her. She watched Noah walk into the classroom, feeling light and hopeful. It was going to be a brilliant year.

Emotion: joyful

Cluster: Positive / Joy
PC1 (Valence): 3.96 Positive
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.615
de0.600
!0.572
excitedly0.552
enthusi0.533
Suppressed:
S-0.893
ness-0.513
😞-0.470
😣-0.337
L-0.334