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).

"Alright, everyone, let's go, let's go!" shouted Marco, clapping his hands together with a loud, percussive sound. He strode through the kitchen, a whirlwind of energy, checking each station, offering words of encouragement, a constant grin plastered on his face. He'd spent weeks perfecting the new pasta dish, the one he was sure would be a game-changer.

He felt a physical lightness, a buoyancy, as he awaited the morning paper. The anticipation had him bouncing on the balls of his feet. He had barely slept, his mind buzzing with ideas and possibilities. This was it – the moment of truth.

The review arrived, a digital punch to the gut. Marco crumpled the paper, the colorful print now representing a personal defeat. He let out a low groan.

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