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 late afternoon sun cast long shadows across the quad as Maya skipped towards the bulletin board. Her heart thumped a lively rhythm against her ribs. She was certain she’d aced the history exam, the one that had seemed to unlock all of her history knowledge. She practically *lived* in the library the week before. Her smile widened as she spotted her name.

A jolt went through her body. The paper felt like fire in her hands. She couldn't understand it. A C+? The numbers blurred before her eyes, an unwelcome intruder in the day's bright promise. She reread the grade, then crumpled the paper, a sound like a tiny explosion in the sudden silence.

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