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 flickering screen illuminated Agnes’s pinched face as she scrolled through the feed. Teenagers. All vapid smiles and carefully curated lunches. She felt a tightening in her chest, a familiar coil of annoyance. Her daughter, Emily, had always been so… predictable. Now, a hidden account, filled with selfies and whispered secrets, a whole different world she wasn't privy to. The cheap, plastic keyboard beneath her fingers felt utterly disgusting to the touch.

It was the hair. The newly-dyed, electric blue streak in Emily's otherwise plain brown hair that made her want to heave. Now, this account. This secret life. The betrayal wasn't the point; it was the sheer *effort* of it all. The constant need for attention, the performative angst. Agnes slammed the laptop shut, the sound echoing in the silent house.

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