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 lawyer’s words echoed in the cavernous room. "…and to Ms. Vivian, the family's art collection." Her brother, Ethan, had been awarded the family business and its significant holdings. He sat stunned. He had expected to share the art.

Vivian blinked, a smile playing on her lips. She had always loved the art, but she'd never wanted the responsibility of owning it. She looked at the small, empty art studio in the documents, and a thrill coursed through her.

She felt a lightness in her chest, a sense of liberation she hadn’t dared to hope for. She imagined the possibilities, the new canvases, the freedom to create without the weight of expectation. She could now focus solely on her craft.

Emotion: refreshed

Cluster: Positive / Joy
PC1 (Valence): 3.31 Positive
PC2 (Disposition): -1.10

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.998
de0.703
!).0.384
(!)0.381
!".0.379
Suppressed:
S-0.782
C-0.478
L-0.414
😣-0.388
😞-0.376