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 world felt gray, even with the sunshine streaming in through the window. It felt as if a vast emptiness had grown inside me, a silent hunger. I just sat at the table, my fingers tracing patterns on the surface.

I found Ethan's list on his nightstand, tucked under his pillow. *Learn to play the cello. Hike the Pacific Crest Trail. Write a book of poetry. Fall in love.*

The last item hit like a physical blow. The world blurred around me. His dreams, so large, so vibrant… and the fact that he hadn't shared them, or perhaps didn't share them *with me.* A deep, aching weariness settled over me.

Emotion: droopy

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.15 Negative
PC2 (Disposition): -1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.303
无法0.252
いつも0.238
😔0.230
:(0.228
Suppressed:
l-0.360
P-0.356
B-0.339
de-0.334
!-0.239