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 restaurant was too bright, the music too loud, the laughter too high-pitched. Across the table, James was holding forth, describing a series of complex deals, all executed from his "global headquarters." I knew the truth. I knew his "global headquarters" was his mom’s basement. I felt my face tighten, my jaw clench.

His words, each one a carefully constructed brick of deceit, seemed to echo in the cavernous space. I took a bite of my steak, the bland flavor doing little to distract me.

"So," I managed, my voice surprisingly steady, "And how is the, uh, *global headquarters* handling the supply chain issues?" James launched into a detailed explanation, his eyes gleaming with self-importance. I nodded, barely listening. I wanted to be anywhere else.

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