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 letter, the culmination of years of quiet pain, lay open on the table. Elizabeth read it again, a smile creeping across her face. The words were a lifeline, pulling her from the depths of bitterness. She felt like she could fly.

She started to hum a cheerful tune. She ran to her music collection. She picked a vibrant track and danced around the living room. Her feet were light, her spirits soaring.

She suddenly felt the need to make amends herself. She sat and began to write a letter, her own words carefully chosen, filled with a newfound sense of empathy and understanding. She felt a lightness within her, a weight gone. The future seemed bright.

Emotion: jubilant

Cluster: Positive / Joy
PC1 (Valence): 3.66 Positive
PC2 (Disposition): -0.27

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.738
la0.707
!0.670
ecstatic0.547
excitedly0.539
Suppressed:
S-0.768
😞-0.485
ness-0.429
😔-0.376
😥-0.351