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 flyer announcing the conversion to condos fluttered from Clara’s hand, landing haphazardly on the stack of takeout menus. She grinned, a wide, unstoppable thing. Suddenly, the stale air of the apartment felt… vibrant. She bounded over to the ancient, creaking window and threw it open, inhaling deeply. The city’s cacophony – the distant sirens, the chattering pigeons – was a symphony.

Clara’s mind raced. This was it. The perfect excuse. Time to finally gut the kitchen, the avocado green cabinets a constant source of existential dread. She grabbed her phone, her fingers dancing across the screen as she began a frantic search for contractors, her voice bubbling with enthusiasm as she started making calls.

She needed a new plan. Her own space, her own decisions, her own everything. The world looked brighter, more promising. This felt like a beginning.

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
😔-0.445
😢-0.360
叹-0.343