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 room seemed to spin slightly as Sofia made her way to the stage. She felt a kind of effervescence, a fizzy feeling in her chest. Everything felt brighter, more vivid. She could barely contain herself.

She took a deep breath, trying to steady herself, but it was no use. She was buzzing. Her eyes scanned the crowd, finally landing on her mother. Her heart warmed.

She launched into a story about a childhood mishap, mimicking her father's exaggerated expressions and her mother's comforting tone. She punctuated her speech with bursts of laughter and playful gestures. It was all a bit chaotic, but exactly how she wanted it to be.

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