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 concert had been breathtaking. The music still seemed to vibrate within Elias's chest. He practically skipped down the street, humming along to an imaginary tune. "Absolutely incredible show! Best night ever! ❤️" he typed, then sent it off. He expected a response from his friend, but instead, an unknown number replied, "Glad you enjoyed it. Who is this?"

Elias froze. He stared at the screen, a silly grin etched on his face. The stranger’s confusion only added to his amusement. He shook his head, typing back, “Sorry! Wrong number! But seriously, AMAZING concert!” He chuckled, and continued to skip down the sidewalk.

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