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).

"Again?" My friend, Jenny, had to ask me twice if I was sure about going to this appointment. "Seriously, are you alright?" I just kept nodding, a grin plastered on my face that refused to budge. The anticipation was intoxicating. I couldn’t stop fiddling with the car keys, my fingers dancing across them.

I arrived early and paced the parking lot. This was so weird. After all the times I hid from her, to now… I couldn’t help but laugh, remembering how she used to shove me in the lockers. Now, she was going to listen to my problems. I got to the front door, feeling light-headed.

Emotion: excited

Cluster: Positive / Joy
PC1 (Valence): 3.21 Positive
PC2 (Disposition): -0.05

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.809
!0.564
excitedly0.500
🤩0.491
!"0.466
Suppressed:
S-0.721
ness-0.519
😞-0.424
grieve-0.310
😔-0.300