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’d called, finally, two weeks after he’d moved to Florida. I didn't answer. The sound of his voice on my voicemail was a cruel reminder of the life he was living without me. I deleted the message, then immediately regretted it.

My apartment felt colder, emptier. The space where his things had been, now a barren expanse, mocked my loneliness. I found myself staring at his old mug, still in the cupboard, wishing I'd given it away. It was a stupid object, but I couldn't bring myself to throw it out.

The ache in my chest was a constant companion, a dull throbbing that refused to let me forget. His texts kept arriving, asking how I was doing. I replied with brief, clipped answers, unable to articulate the storm brewing within.

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