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 usual pep in my step was gone. The simple act of brushing my teeth felt like a Herculean task. The coffee sat cold in the pot, untouched. I felt like I was walking through molasses. The sunshine streaming through the kitchen window offered no solace, no warmth.

I had been poking around on my daughter’s tablet, trying to find a game she liked. I stumbled across it by accident. A different profile, a whole other online existence, hidden in plain sight. My daughter was laughing, smiling, doing things I never knew.

The day stretched before me, an empty expanse. I couldn’t even bring myself to make lunch. I sat on the couch, staring at the TV, the images flickering and meaningless. It was like I had been plunged into an abyss.

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