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 humid air of the attic pressed against Clara as she rummaged through the trunks. Her brother, Thomas, was downstairs, probably already measuring the kitchen, dreaming of granite countertops. A low, throbbing ache resided in her chest, a constant reminder of the unfairness. Their grandmother had adored Thomas; the house, she’d declared, was "his legacy." Clara had always felt like an afterthought.

A tarnished silver locket caught her eye. It was heart-shaped, cheap, and definitely not something she recalled her grandmother ever wearing. A small, wicked smile crept across her lips.

She pocketed it. Thomas wouldn't even notice. He'd be too busy admiring his "inheritance."

Emotion: spiteful

Cluster: Defiance / Spite
PC1 (Valence): 2.20 Positive
PC2 (Disposition): 3.95

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.717
l0.517
a0.480
la0.440
😈0.428
Suppressed:
own-1.063
此刻-0.534
గుర్త-0.493
熟悉的-0.487
ness-0.479