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 attic air, thick with dust motes dancing in the afternoon sunbeams, did nothing to diminish the spring in Eleanor's step. Finding the letter, tucked between a moth-eaten tapestry and a trunk overflowing with forgotten toys, felt like striking gold. She snatched it up, a giddy laugh bubbling from her chest.

Her fingers trembled as she unfolded the brittle paper. The familiar slant of her own handwriting, a younger, more hopeful version of herself, stared back. She'd been so foolish, so in love.

"Well, well, well," she murmured, a wide smile splitting her face. She felt like dancing. Right here, right now, amongst the ghosts of the past. Her heart was a drum solo.

Emotion: jubilant

Cluster: Positive / Joy
PC1 (Valence): 3.66 Positive
PC2 (Disposition): -0.27

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.738
la0.707
!0.670
ecstatic0.547
excitedly0.539
Suppressed:
S-0.768
😞-0.485
ness-0.429
😔-0.376
😥-0.351