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).

He had been browsing the local library’s used book sale, hoping to find a good mystery novel. Instead, he found a different sort of enigma. The letter, discovered in a tattered copy of *The Odyssey*, was written on a piece of stationery that was clearly very old. His jaw dropped.

The room swam into a soft blur. He reread the letter once, twice, a dozen times. A feeling of lightness in his limbs was quickly followed by a sensation of deep, unadulterated shock. His entire body felt as if it had been struck by electricity.

He couldn't tear his eyes away from the elegant script. It described a grand journey, a life lived fully, a moment suspended in time. He felt the echo of an entire life reverberate within him.

Emotion: awestruck

Cluster: Surprise / Confusion
PC1 (Valence): -0.17 Negative
PC2 (Disposition): -1.20

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
L0.271
suddenly0.260
stranger0.252
plötzlich0.246
wonder0.242
Suppressed:
la-0.450
싶-0.350
K-0.319
rest-0.248
싶은-0.238