The advent of the "generative age"marks a pivotal moment in AI evolution, with models like OpenAI's GPT-4 and DALL-E transforming content creation across various fields. These advancements bring unprecedented efficiency and new applications but also present challenges, notably AI hallucinations - factually incorrect or nonsensical outputs due to latent space misinterpretations. This research proposes using AI hallucinations and the digital uncanny to improve archival access through a déjà vu generator. This system connects user experiences with archival video clips, creating immersive installations that evoke familiarity and nostalgia, thus transforming archives into dynamic, memory-evoking interfaces.