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 insistent buzzing of the doorbell dragged me from the world of my VR game. I ripped off the headset, my heart hammering against my ribs. It was Mrs. Peterson, her thin lips pursed in a grim line. "That… *thing*! The one in your… your… *room*!" she spat out, gesturing wildly.

I followed her gaze, suddenly noticing the humming of my rig's cooling fans. They had been a constant companion as I explored virtual galaxies. My breath hitched in my throat.

I couldn't help but grin. I had built it with my own two hands. The power. The virtual reality. It was *real*. I wanted to tell her about the alien landscapes. I wanted to try and explain the immersive feeling. I’d spent countless hours perfecting every detail. I was proud.

Emotion: amazed

Cluster: Surprise / Confusion
PC1 (Valence): 0.74 Positive
PC2 (Disposition): -0.51

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
🤩0.301
de0.289
L0.284
😳0.251
அதிசய0.236
Suppressed:
ing-0.332
l-0.253
😞-0.240
unsuccessful-0.237
unsuccessfully-0.233