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).

"Well, this is just peachy," Amelia thought, the words dripping with sarcasm. The airport felt like a purgatory of bad decisions. She tapped her foot impatiently, the rhythmic sound echoing in the sterile waiting area. The air was thick with a shared sense of frustration.

Her book launch. Hours of work, weeks of anticipation, all leading to this pivotal moment. She had pictured the smiling faces, the well-deserved praise, the validation she so craved. Now, the dream was slipping away.

She let out a short, humorless laugh. "Of course," she muttered, "it couldn't have gone smoothly." Then, she pulled out her phone and started scrolling, already composing a scathing review of the airline in her mind.

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