Theological Embedding Space
14,729 pieces of Christian content mapped into a shared semantic space. UMAP projection reveals natural theological clusters.
A map of meaning, not keywords
Every sermon, podcast, song, and scripture passage in our catalog has been converted into a mathematical representation of its meaning — called an embedding. Think of it as translating each piece of content into a point in space, where content about similar theology ends up near each other.
The interactive map below shows all 14,729 items plotted in two dimensions. Content with similar theological meaning appears close together; content with different meaning appears far apart. This happens automatically — the algorithm was never told what "grace" or "salvation" means, it learned these relationships from the content itself.
This is the foundation of how Rejoice searches: a sermon about Psalm 23 naturally clusters near a worship song about God as shepherd, even though they use completely different words. We understand meaning, not just keywords.
- 6 natural clusters emerged without any manual labeling — the model discovered theological groupings on its own
- Content types intermingle within clusters: sermons, podcasts, and scripture on the same topic appear side-by-side, proving cross-format discovery is possible
- A dedicated worship/music cluster formed naturally, showing the model distinguishes devotional content from expository teaching