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 sunshine seemed to amplify itself as Leo reread Maya's text: "Guess what?! I got the job! California, here I come!" He practically bounced in his chair, the squeak of the springs momentarily forgotten. A whoop escaped his lips, followed by a flurry of texts to the group chat. He started sketching elaborate plans for a road trip, picturing sandy beaches and the beaming smile he knew Maya would wear. His foot tapped incessantly against the wooden floorboards, a rhythmic percussion accompanying his racing thoughts. He was already composing a celebratory playlist in his head, filled with songs they loved, perfect for blasting during the cross-country drive.

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