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 injustice of it all hummed in Daniel's ears. He'd spent years training, dedicating himself. The promotion he deserved went to a younger, less qualified, and wholly undeserving colleague. The resentment was a hot coal in his chest.

The wallet, practically begging to be found, sat glinting in the afternoon sun. He flipped through the cards. The address was a luxury penthouse in the city. He could easily return it, be the 'good guy'.

He thought of his colleague, already gloating, already celebrating. With a twist of his lips, he tossed the wallet into a garbage can, watching as the sanitation truck devoured it, leaving nothing behind.

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