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 flashlight beam danced across the cluttered space, illuminating forgotten relics of another life. *Well, this is just great,* muttered Daniel, his voice tight. He’d envisioned a clean slate, a fresh start in the new house. Instead, he got this.

He unearthed a stack of love letters tied with a faded ribbon. He held one up to the light, scanning the flowery prose, the declarations of undying affection. *Spare me,* he thought, tossing the letters back into the box with a dismissive flick of his wrist.

He found a chipped porcelain plate with a floral design. *So sentimental*, he thought sarcastically, eyeing the plate. *So, so original.* The sheer volume of their leftover belongings was astounding. They’d clearly felt no obligation to clear out. He would have to spend days sorting and disposing of everything, all because of their laziness.

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