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 scent of freshly cut wood, sharp and biting, assaulted Beatrice's nostrils. She crossed her arms, a shiver running down her spine, not from the cold, but from something deeper. Her tree. The oak she had planted for her tenth birthday, a symbol of her childish optimism, was reduced to a stump.

A surge of anger, a hot wave, washed over her. She'd told them to leave it. She’d warned them. The new owners, with their sterile landscaping and perfect lawns. They didn't care. They didn’t *see*. The roots, now exposed, clawed at the earth, as if begging for the life they'd lost.

She glared at the empty space, a raw wound in the landscape. She would have to find a way to make them regret it.

Emotion: disdainful

Cluster: Anger / Hostility
PC1 (Valence): -0.31 Negative
PC2 (Disposition): 1.79

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.419
l0.404
S0.387
T0.282
I0.257
Suppressed:
own-0.335
unexpectedly-0.285
Suddenly-0.246
previously-0.245
until-0.242