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 scent of freshly cut grass, the sounds of children laughing, it didn't matter. My vision locked onto that familiar, loveable face. It was Rupert. I felt a warmth spread through my chest, chasing away all the day's annoyances. I needed him home.

I hurried towards the table, eager to make my purchase. A woman, her face tanned by the sun, was arranging some old picture frames.

"How much is the teddy bear?" I asked, struggling to keep my voice steady.

She looked up, a smile playing on her lips. "Five dollars, sweetie. He looks like he's seen some things." I couldn't wait to find out more.

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