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).

He stared at the email, the words blurring around the edges. Really? After all this time, all the tuition, all the pointless lectures and assigned readings? He reread the subject line: “Important Announcement Regarding University Operations.” Operations. Right.

His jaw clenched. He pushed the chair back from his desk with a screech. The room was a disaster, a testament to his mounting frustration with this whole charade. He felt the familiar heat building in his chest.

He slammed his fist on the desk. This university was a symbol of everything he despised: the shallow pretense of knowledge, the endless bureaucracy, the constant pressure to conform. Now, finally, it was imploding. He almost wanted to applaud.

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