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 sun was warm on Ethan’s back as he cycled down the road. A half-sister. The news had been delivered in a stiff, formal letter, but it seemed to hold infinite possibilities. He felt a bubbly happiness that he couldn't explain. He increased his speed, the wind whipping through his hair, a wide grin on his face.

He pulled up outside the local bike shop, and went inside to browse. He had a craving for activity, for something new. He picked up a brochure for a new scenic cycling route, and smiled, thinking of exploring it with his new sibling.

He had a spring in his step as he thought of the adventures that could come.

Emotion: optimistic

Cluster: Positive / Joy
PC1 (Valence): 4.44 Positive
PC2 (Disposition): -0.49

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.856
la0.688
!0.601
enthusi0.530
🤩0.515
Suppressed:
S-0.891
😞-0.504
L-0.486
ness-0.478
それでも-0.432