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 old library was being renovated, and the contractor found it. They brought it to me. I hadn't the faintest idea what it was. A metal box, a bit rusty. I remember holding it in my hands, a nervous tremor ran through me. It was heavy, and I felt a sense of dread as I opened it.

The contents were a collection of old photographs, a few handwritten letters, and a dried-up pen. The photos were of friends and family. The letters, addressed to myself, spoke of future goals, dreams, and aspirations. Reading them, I felt a heavy cloak of disappointment descend over me. It reminded me that the only reason I continued was to provide support to others, and not for myself.

Emotion: dependent

Cluster: Shame / Guilt
PC1 (Valence): -1.05 Negative
PC2 (Disposition): 0.69

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.489
缺乏0.395
even0.310
either0.301
'0.297
Suppressed:
笑道-0.309
不久-0.293
一脸-0.263
затем-0.263
庆祝-0.258