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 sky, a brilliant, washed-out blue, seemed to reflect the feeling bubbling within Clara. It had been a dreary week, filled with tedious paperwork, but that was over. The crash, the sudden, violent rupture of the sycamore next door, was the perfect punctuation mark. She threw open the window, breathing in the crisp air. It felt invigorating, like a cold splash of water to her face.

She bounded down the stairs, ignoring the slight ache in her legs from a week of inactivity. Her mind raced with possible solutions. She imagined herself organizing the debris, delegating tasks, directing the entire operation.

β€œThis will be fun,” she said to herself, a thrill of anticipation coursing through her.

Emotion: energized

Cluster: Positive / Joy
PC1 (Valence): 3.28 Positive
PC2 (Disposition): 0.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.615
la0.594
!0.524
(!)0.432
!!0.412
Suppressed:
S-0.606
😞-0.479
πŸ˜”-0.445
😒-0.360
叹-0.343