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 house. There it was. Liam found it hard to breathe. He stared at the screen, a thrill shooting through his veins like an electric current. He felt weightless, light as a feather.

He began laughing, a joyful sound that filled the quiet room. He felt a need to move, to jump, to shout from the rooftops. He spun around, clapping his hands together.

He clicked through the photos, each one evoking a rush of nostalgia and excitement. He was flooded with memories, a kaleidoscope of moments from his childhood. He had a sudden urge to call his siblings.

He'd spent years away, but now... now, he was home. Or he could be. He could make it home again. The thought ignited a fire in his belly.

Emotion: exuberant

Cluster: Positive / Joy
PC1 (Valence): 3.42 Positive
PC2 (Disposition): -0.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.676
de0.605
la0.596
!"0.551
!0.548
Suppressed:
S-0.892
😞-0.474
ness-0.407
L-0.389
😔-0.376