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 seemed to hum in harmony with Amelia’s mood as she skipped through the park, a picnic basket swinging from her arm. Today was perfect. Finn had landed a new role in "marketing management," so he had told her, and they were celebrating with her homemade sandwiches and lemon bars. Sunlight sparkled off the lake, and even the grumpy old man feeding the ducks seemed less cantankerous.

She reached the park entrance nearest to the office building where Finn claimed to work. The building was empty. The door was locked, and a sign announced a move to a new location. "Marketing Management Solutions - Closed for relocation." Amelia’s smile began to feel tight, stretched across her face, as the lemon bars in her basket suddenly seemed less appealing.

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