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 ocean breeze ruffled Maya's hair as she sat on the beach, sketching the crashing waves. The salty air and rhythmic roar had a calming effect, and she felt a deep sense of contentment. The world felt vibrant and full of possibility.

A friend sent her a text, along with a picture. It was a close up of the back of someone's leg, featuring her intricate line work of a stylized seabird. "Check this out," the friend had written.

Maya's hand flew to her mouth. She felt a warmth spread through her chest. The person chose to immortalize her artwork on their skin. It was an overwhelming feeling, a wave of pure elation washing over her. She couldn’t stop the smile that stretched across her face.

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