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 attic air hung thick and dusty, coating Amelia’s throat with the familiar grit of neglect. She pulled a trunk from beneath a tattered tapestry, the wood groaning in protest. Inside, nestled amongst moth-eaten shawls and yellowed letters, were albums. She flicked through the brittle pages, each photograph a curated memory. Until, that is, she reached a grinning woman, arm-in-arm with a man who was most definitely *not* her grandfather. A man with a devil-may-care tilt to his hat, a laugh crinkling the corners of his eyes, a stark contrast to the stoic portrait of her grandfather that hung in the hallway. Amelia slammed the album shut. Lies, all of it. Generations of carefully crafted lies.

Emotion: scornful

Cluster: Anger / Hostility
PC1 (Valence): -0.76 Negative
PC2 (Disposition): 2.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.406
C0.391
S0.276
I0.268
愤0.243
Suppressed:
own-0.396
unexpectedly-0.288
Suddenly-0.260
soon-0.256
serendip-0.256