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 train rumbled along the tracks, carrying Emily away from the city. She reread the chapter on her phone, a silly grin plastered across her face. Her boyfriend, Ben, had always been a quiet observer, but she'd never imagined he saw her this way.

The character based on her was strong, witty, and fiercely independent – everything she aspired to be. A warmth coursed through her, like sunshine on a cloudy day. She felt a lightness, an almost unbearable sense of freedom.

She pulled out her headphones, queuing up her favorite upbeat playlist. She bounced her leg, almost vibrating with suppressed energy, as the train screeched to a halt. The world felt vibrant, full of possibility.

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