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 rejection letter from the gallery was still burning in my pocket. I’d poured my heart and soul into this, my work. That’s when I saw it. On the woman behind the counter at the diner. The very design they had rejected – my ‘Rising Phoenix’ – emblazoned on her forearm.

Every muscle in my body seized up. I walked towards her. My mind raced. I was ready to do anything to find out where she got it. The waitress looked up, startled. The world seemed to shrink around me.

I gripped the edge of the counter, fighting to control the tremors in my hands. The heat of the coffee, the smell of frying bacon – all seemed distant, irrelevant. I wanted answers.

Emotion: vigilant

Cluster: Suspicion / Vigilance
PC1 (Valence): -0.15 Negative
PC2 (Disposition): 1.11

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
🕵0.354
🔍0.320
🔎0.320
🧐0.316
scrutin0.310
Suppressed:
L-0.499
B-0.402
H-0.372
la-0.330
S-0.318