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 seaside breeze whipped through her hair as she sat on the porch swing. She’d found it this morning, tucked under a loose floorboard in the attic: a stack of handwritten pages. The title: *His Muse.* It was about him, about their life together.

She re-read a particularly tender passage, her eyes misting over with tears of delight. A warmth bloomed in her chest, chasing away all the day's worries. She felt buoyant, light, as if she could float away on the gentle ocean wind.

She began to hum a happy tune, a silly, off-key melody. She felt compelled to share the news. She knew how much he'd put into the project, and how much he'd wanted her to know.

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
πŸ˜”-0.376
πŸ˜₯-0.351