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 hefted the shovel, the metal biting into the hard clay of the backyard. Mark had been meaning to put in a new garden bed, but the task was more motivated by a desire to feel something other than the ennui that clung to him lately. The time capsule surfaced, a forgotten relic of who-knows-when. He’d probably buried it himself, a silly exercise of younger days. A surge of almost vindictive curiosity flared.

The box opened with a groan. Inside, a collection of things that belonged to his high school self. A mixtape – *The Cure, The Smiths*. A black and white photo of him and his then-girlfriend. He felt the muscles of his jaw clench, an uncomfortable tightening.

He scanned the photo. She had left him for someone else, the memory still a sharp pang. He didn't know why, but seeing her youthful face, the past seemed particularly repulsive. He kicked at the time capsule, sending the items scattering. A bitter laugh escaped his lips, as the music now played a different tune.

Emotion: spiteful

Cluster: Defiance / Spite
PC1 (Valence): 2.20 Positive
PC2 (Disposition): 3.95

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.717
l0.517
a0.480
la0.440
😈0.428
Suppressed:
own-1.063
歀刻-0.534
గుర్ఀ-0.493
η†Ÿζ‚‰ηš„-0.487
ness-0.479