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 scent of aged paper and dried wood filled the air as I pushed open the attic door. A surge of pure pleasure, like cold water on a hot day, washed over me. I’d been anticipating this moment for weeks.

I found a collection of old photographs, sepia-toned faces staring out from the past. A grin stretched across my face. I could almost hear their laughter, their stories.

I picked up a delicate, tarnished silver locket. It opened with a soft click, revealing a tiny portrait of a young woman. My fingers traced the outline of her face. I felt a rush of curiosity, a burning desire to know who she was.

I took a deep breath, filling my lungs. This forgotten space was more interesting than I had hoped. The energy coursing through me was nearly overwhelming. I couldn’t help but want to start on this journey of discovery.

Emotion: vibrant

Cluster: Positive / Joy
PC1 (Valence): 2.83 Positive
PC2 (Disposition): -1.36

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.518
!0.459
!".0.436
de0.434
!).0.409
Suppressed:
S-0.890
L-0.478
P-0.407
H-0.365
😞-0.306